diff options
author | Soumith Chintala <soumith@gmail.com> | 2016-10-14 01:31:33 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2016-10-14 01:31:33 +0300 |
commit | 4d123cd81ebfc2c22d022dad67a7c0116e167f51 (patch) | |
tree | 23e123ae4225f7cfb211a7486466028f89736dc5 | |
parent | 817910bb2576e1b3a9848e63ea2052d3dc0636d9 (diff) | |
parent | 298d56013488955e208d632c2a424c0c98be4e56 (diff) |
Merge pull request #271 from Amir-Arsalan/patch-1
Update README.md
-rw-r--r-- | README.md | 5 |
1 files changed, 4 insertions, 1 deletions
@@ -10,7 +10,8 @@ Conversion between `nn` and `cudnn` is available through `cudnn.convert` functio * Install cuDNN (version R5 EA) * Have at least CUDA 7.0 -* Have `libcudnn.so` in your library path (Install it from https://developer.nvidia.com/cuDNN ) +* Have `libcudnn.so` in your library path ($LD_LIBRARY_PATH) (Install cuDNN it from https://developer.nvidia.com/cuDNN ) +* Instead of the previous step, you can copy the library files into /usr/local/cuda/lib64/ or to the corresponding folders in CUDA directory #### Modules @@ -90,6 +91,8 @@ If you don't want to convert all modules you can pass a function as the third ar It will be called at each step, with a module that is currently converted. It is meant to exclude modules i.e. if it returns `true`, they will be left untouched, otherwise they will be subject to conversion. +`Note that you cannot do backward pass when using cuDNN and when your model has batch normaliation layers and is in evaluate mode.` + ```lua net = nn.Sequential() net:add(nn.SpatialConvolution(3,96,11,11,3,3)) |